Commit
•
1c0d312
1
Parent(s):
22ed348
Training in progress, epoch 0
Browse files- all_results.json +8 -0
- pytorch_model.bin +1 -1
- runs/Jul06_10-34-29_512daece0cbe/events.out.tfevents.1657103727.512daece0cbe.74.0 +2 -2
- runs/Jul06_10-45-23_512daece0cbe/1657104335.281916/events.out.tfevents.1657104335.512daece0cbe.74.3 +3 -0
- runs/Jul06_10-45-23_512daece0cbe/events.out.tfevents.1657104335.512daece0cbe.74.2 +3 -0
- train_results.json +8 -0
- trainer_state.json +229 -0
- training_args.bin +1 -1
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 19.73,
|
| 3 |
+
"total_flos": 5.187420432666501e+17,
|
| 4 |
+
"train_loss": 0.4364403486251831,
|
| 5 |
+
"train_runtime": 567.1784,
|
| 6 |
+
"train_samples_per_second": 11.954,
|
| 7 |
+
"train_steps_per_second": 0.071
|
| 8 |
+
}
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 346858475
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:52f393aeda5284a3f19b6b4b511daec82fe07d035f0561e5ca597dbcb6da0870
|
| 3 |
size 346858475
|
runs/Jul06_10-34-29_512daece0cbe/events.out.tfevents.1657103727.512daece0cbe.74.0
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:eb2c7729a14271f4260b735b250d6ca8a090c7378535b8a850c80dbe81194a88
|
| 3 |
+
size 11569
|
runs/Jul06_10-45-23_512daece0cbe/1657104335.281916/events.out.tfevents.1657104335.512daece0cbe.74.3
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:317f5607cf0fb90176cfe8c9c727d5e928cc79066b24275465ca99ffd2c950bb
|
| 3 |
+
size 5411
|
runs/Jul06_10-45-23_512daece0cbe/events.out.tfevents.1657104335.512daece0cbe.74.2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:21663d0c8dff0bb6f06286c0f5565e84f94bfe353b6a5a5b084448ba27ff4b60
|
| 3 |
+
size 4630
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 19.73,
|
| 3 |
+
"total_flos": 5.187420432666501e+17,
|
| 4 |
+
"train_loss": 0.4364403486251831,
|
| 5 |
+
"train_runtime": 567.1784,
|
| 6 |
+
"train_samples_per_second": 11.954,
|
| 7 |
+
"train_steps_per_second": 0.071
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,229 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.910958904109589,
|
| 3 |
+
"best_model_checkpoint": "beit-base-patch16-224-pt22k-ft22k-rim_one-new/checkpoint-30",
|
| 4 |
+
"epoch": 19.727272727272727,
|
| 5 |
+
"global_step": 40,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.73,
|
| 12 |
+
"eval_accuracy": 0.4794520547945205,
|
| 13 |
+
"eval_loss": 0.6921706199645996,
|
| 14 |
+
"eval_runtime": 25.0333,
|
| 15 |
+
"eval_samples_per_second": 5.832,
|
| 16 |
+
"eval_steps_per_second": 0.2,
|
| 17 |
+
"step": 2
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 1.73,
|
| 21 |
+
"eval_accuracy": 0.6506849315068494,
|
| 22 |
+
"eval_loss": 0.7311218976974487,
|
| 23 |
+
"eval_runtime": 4.1824,
|
| 24 |
+
"eval_samples_per_second": 34.909,
|
| 25 |
+
"eval_steps_per_second": 1.195,
|
| 26 |
+
"step": 4
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 2.73,
|
| 30 |
+
"eval_accuracy": 0.4178082191780822,
|
| 31 |
+
"eval_loss": 0.9364489316940308,
|
| 32 |
+
"eval_runtime": 4.1884,
|
| 33 |
+
"eval_samples_per_second": 34.858,
|
| 34 |
+
"eval_steps_per_second": 1.194,
|
| 35 |
+
"step": 6
|
| 36 |
+
},
|
| 37 |
+
{
|
| 38 |
+
"epoch": 3.73,
|
| 39 |
+
"eval_accuracy": 0.7945205479452054,
|
| 40 |
+
"eval_loss": 0.4742239713668823,
|
| 41 |
+
"eval_runtime": 4.2915,
|
| 42 |
+
"eval_samples_per_second": 34.021,
|
| 43 |
+
"eval_steps_per_second": 1.165,
|
| 44 |
+
"step": 8
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 4.73,
|
| 48 |
+
"learning_rate": 8.333333333333334e-05,
|
| 49 |
+
"loss": 0.8198,
|
| 50 |
+
"step": 10
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 4.73,
|
| 54 |
+
"eval_accuracy": 0.8561643835616438,
|
| 55 |
+
"eval_loss": 0.36144283413887024,
|
| 56 |
+
"eval_runtime": 4.4462,
|
| 57 |
+
"eval_samples_per_second": 32.837,
|
| 58 |
+
"eval_steps_per_second": 1.125,
|
| 59 |
+
"step": 10
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 5.73,
|
| 63 |
+
"eval_accuracy": 0.8561643835616438,
|
| 64 |
+
"eval_loss": 0.3010813593864441,
|
| 65 |
+
"eval_runtime": 4.3245,
|
| 66 |
+
"eval_samples_per_second": 33.761,
|
| 67 |
+
"eval_steps_per_second": 1.156,
|
| 68 |
+
"step": 12
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 6.73,
|
| 72 |
+
"eval_accuracy": 0.8561643835616438,
|
| 73 |
+
"eval_loss": 0.2709261178970337,
|
| 74 |
+
"eval_runtime": 4.3245,
|
| 75 |
+
"eval_samples_per_second": 33.761,
|
| 76 |
+
"eval_steps_per_second": 1.156,
|
| 77 |
+
"step": 14
|
| 78 |
+
},
|
| 79 |
+
{
|
| 80 |
+
"epoch": 7.73,
|
| 81 |
+
"eval_accuracy": 0.6027397260273972,
|
| 82 |
+
"eval_loss": 0.7967002987861633,
|
| 83 |
+
"eval_runtime": 4.3664,
|
| 84 |
+
"eval_samples_per_second": 33.437,
|
| 85 |
+
"eval_steps_per_second": 1.145,
|
| 86 |
+
"step": 16
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 8.73,
|
| 90 |
+
"eval_accuracy": 0.8287671232876712,
|
| 91 |
+
"eval_loss": 0.39434078335762024,
|
| 92 |
+
"eval_runtime": 4.348,
|
| 93 |
+
"eval_samples_per_second": 33.578,
|
| 94 |
+
"eval_steps_per_second": 1.15,
|
| 95 |
+
"step": 18
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 9.73,
|
| 99 |
+
"learning_rate": 5.555555555555556e-05,
|
| 100 |
+
"loss": 0.5673,
|
| 101 |
+
"step": 20
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 9.73,
|
| 105 |
+
"eval_accuracy": 0.8835616438356164,
|
| 106 |
+
"eval_loss": 0.2661159336566925,
|
| 107 |
+
"eval_runtime": 4.3636,
|
| 108 |
+
"eval_samples_per_second": 33.458,
|
| 109 |
+
"eval_steps_per_second": 1.146,
|
| 110 |
+
"step": 20
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 10.73,
|
| 114 |
+
"eval_accuracy": 0.7671232876712328,
|
| 115 |
+
"eval_loss": 0.4626728296279907,
|
| 116 |
+
"eval_runtime": 4.4331,
|
| 117 |
+
"eval_samples_per_second": 32.934,
|
| 118 |
+
"eval_steps_per_second": 1.128,
|
| 119 |
+
"step": 22
|
| 120 |
+
},
|
| 121 |
+
{
|
| 122 |
+
"epoch": 11.73,
|
| 123 |
+
"eval_accuracy": 0.8835616438356164,
|
| 124 |
+
"eval_loss": 0.24509218335151672,
|
| 125 |
+
"eval_runtime": 4.4007,
|
| 126 |
+
"eval_samples_per_second": 33.177,
|
| 127 |
+
"eval_steps_per_second": 1.136,
|
| 128 |
+
"step": 24
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 12.73,
|
| 132 |
+
"eval_accuracy": 0.9041095890410958,
|
| 133 |
+
"eval_loss": 0.23970794677734375,
|
| 134 |
+
"eval_runtime": 4.1384,
|
| 135 |
+
"eval_samples_per_second": 35.279,
|
| 136 |
+
"eval_steps_per_second": 1.208,
|
| 137 |
+
"step": 26
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 13.73,
|
| 141 |
+
"eval_accuracy": 0.8904109589041096,
|
| 142 |
+
"eval_loss": 0.24433596432209015,
|
| 143 |
+
"eval_runtime": 4.1349,
|
| 144 |
+
"eval_samples_per_second": 35.309,
|
| 145 |
+
"eval_steps_per_second": 1.209,
|
| 146 |
+
"step": 28
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 14.73,
|
| 150 |
+
"learning_rate": 2.777777777777778e-05,
|
| 151 |
+
"loss": 0.2571,
|
| 152 |
+
"step": 30
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 14.73,
|
| 156 |
+
"eval_accuracy": 0.910958904109589,
|
| 157 |
+
"eval_loss": 0.24097245931625366,
|
| 158 |
+
"eval_runtime": 4.2188,
|
| 159 |
+
"eval_samples_per_second": 34.607,
|
| 160 |
+
"eval_steps_per_second": 1.185,
|
| 161 |
+
"step": 30
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 15.73,
|
| 165 |
+
"eval_accuracy": 0.8904109589041096,
|
| 166 |
+
"eval_loss": 0.2714996933937073,
|
| 167 |
+
"eval_runtime": 4.1836,
|
| 168 |
+
"eval_samples_per_second": 34.898,
|
| 169 |
+
"eval_steps_per_second": 1.195,
|
| 170 |
+
"step": 32
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 16.73,
|
| 174 |
+
"eval_accuracy": 0.9041095890410958,
|
| 175 |
+
"eval_loss": 0.2597528100013733,
|
| 176 |
+
"eval_runtime": 4.1231,
|
| 177 |
+
"eval_samples_per_second": 35.41,
|
| 178 |
+
"eval_steps_per_second": 1.213,
|
| 179 |
+
"step": 34
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 17.73,
|
| 183 |
+
"eval_accuracy": 0.8972602739726028,
|
| 184 |
+
"eval_loss": 0.25846657156944275,
|
| 185 |
+
"eval_runtime": 4.1153,
|
| 186 |
+
"eval_samples_per_second": 35.477,
|
| 187 |
+
"eval_steps_per_second": 1.215,
|
| 188 |
+
"step": 36
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 18.73,
|
| 192 |
+
"eval_accuracy": 0.910958904109589,
|
| 193 |
+
"eval_loss": 0.2306668758392334,
|
| 194 |
+
"eval_runtime": 4.1812,
|
| 195 |
+
"eval_samples_per_second": 34.919,
|
| 196 |
+
"eval_steps_per_second": 1.196,
|
| 197 |
+
"step": 38
|
| 198 |
+
},
|
| 199 |
+
{
|
| 200 |
+
"epoch": 19.73,
|
| 201 |
+
"learning_rate": 0.0,
|
| 202 |
+
"loss": 0.1015,
|
| 203 |
+
"step": 40
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"epoch": 19.73,
|
| 207 |
+
"eval_accuracy": 0.8972602739726028,
|
| 208 |
+
"eval_loss": 0.2697519063949585,
|
| 209 |
+
"eval_runtime": 4.1223,
|
| 210 |
+
"eval_samples_per_second": 35.417,
|
| 211 |
+
"eval_steps_per_second": 1.213,
|
| 212 |
+
"step": 40
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 19.73,
|
| 216 |
+
"step": 40,
|
| 217 |
+
"total_flos": 5.187420432666501e+17,
|
| 218 |
+
"train_loss": 0.4364403486251831,
|
| 219 |
+
"train_runtime": 567.1784,
|
| 220 |
+
"train_samples_per_second": 11.954,
|
| 221 |
+
"train_steps_per_second": 0.071
|
| 222 |
+
}
|
| 223 |
+
],
|
| 224 |
+
"max_steps": 40,
|
| 225 |
+
"num_train_epochs": 20,
|
| 226 |
+
"total_flos": 5.187420432666501e+17,
|
| 227 |
+
"trial_name": null,
|
| 228 |
+
"trial_params": null
|
| 229 |
+
}
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 3375
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7b83bbdc3f6dbbe77c082d4f90d6934610ffc2aa729e475ab09f228c21893abb
|
| 3 |
size 3375
|